GeST: A New Image Segmentation Technique based on Graph Embedding

Anthony Perez

2021

Abstract

We propose a new framework to develop image segmentation algorithms using graph embedding, a well-studied tool from complex network analysis. So-called embeddings are low-dimensional representations of nodes of the graph that encompass several structural properties such as neighborhoods and community structure. The main idea of our framework is to first consider an image as a set of superpixels, and then compute embeddings for the corresponding undirected weighted Region Adjacency Graph. The resulting segmentation is then obtained by clustering embeddings. To the best of our knowledge, known complex network-based segmentation techniques rely on community detection algorithms. By introducing graph embedding for image segmentation, we combine two nice properties of aforementioned segmentation techniques, namely working on small graphs with low-dimensional representations. To illustrate the relevance of our approach, we propose GeST, an implementation of this framework using node2vec and agglomerative clustering. We experiment our algorithm on a publicly available dataset and show that it produces qualitative results compared to state-of-the-art segmentation techniques while requiring low computational complexity and memory.

Paper Citation

in Harvard Style

Perez A. (2021). GeST: A New Image Segmentation Technique based on Graph Embedding. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 245-252. DOI: 10.5220/0010191502450252

in Bibtex Style

@conference{visapp21,
author={Anthony Perez},
title={GeST: A New Image Segmentation Technique based on Graph Embedding},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP},
year={2021},
pages={245-252},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010191502450252},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP
TI - GeST: A New Image Segmentation Technique based on Graph Embedding
SN - 978-989-758-488-6
AU - Perez A.
PY - 2021
SP - 245
EP - 252
DO - 10.5220/0010191502450252
PB - SciTePress